A Combined Hardware-Software Approach for Low-Power SoCs: Applying Adaptive Voltage Scaling and Intelligent Energy Management Software

Abstract

Increased functionality and performance demands are challenging System-on-Chip (SoC) designers to seek better methods for optimizing available battery power in portable applications. Key areas of exploration include dynamic voltage scaling and improved software algorithms for the control of power modes. Dynamic voltage scaling can be improved by adaptively monitoring hardware performance to minimize the applied supply voltage for any given clock frequency. While adaptive voltage scaling optimizes power use based on temporal environmental conditions, Intelligent Energy Management (IEM) algorithms optimize power consumption based on the dynamic workload of the processor. IEM software and hardware monitor the execution and communication characteristics of workloads and predictively set the performance of the processor to the level that minimizes energy use, while still meeting application deadlines. The combined use of adaptive voltage scaling and IEM provides the optimum trade-off between performance and battery life for portable devices.